linux-libre-rt-3.12.6_rt9-2: add patch to fix problem causing the kernel to hang on very early in the boot process

2 files changed, 162 insertions, 1 deletions

diff --git a/kernels/linux-libre-rt/PKGBUILD b/kernels/linux-libre-rt/PKGBUILD
index de65bc557..1f6b300ab 100644
--- a/kernels/linux-libre-rt/PKGBUILD
+++ b/kernels/linux-libre-rt/PKGBUILD
@@ -13,7 +13,7 @@ _releasever=6
 _rtpatchver=rt9
 _pkgver=${_basekernel}.${_releasever}
 pkgver=${_basekernel}.${_releasever}_${_rtpatchver}
-pkgrel=1
+pkgrel=2
 _lxopkgver=${_basekernel}.6 # nearly always the same as pkgver
 arch=('i686' 'x86_64' 'mips64el')
 url="http://linux-libre.fsfla.org/"
@@ -32,6 +32,7 @@ source=("http://linux-libre.fsfla.org/pub/linux-libre/releases/${_basekernel}-gn
         'boot-logo.patch'
         'change-default-console-loglevel.patch'
         'criu-no-expert.patch'
+        'timers-do-not-raise-softirq-unconditionally.patch'
         "http://www.linux-libre.fsfla.org/pub/linux-libre/lemote/gnewsense/pool/debuginfo/linux-patches-${_lxopkgver}-gnu_0loongsonlibre_mipsel.tar.bz2")
 md5sums=('254f59707b6676b59ce5ca5c3c698319'
          '4b18ce60daff87504e6740670edf6b50'
@@ -44,6 +45,7 @@ md5sums=('254f59707b6676b59ce5ca5c3c698319'
          '44260d2cb1a8b51c119d2ce1f83e457a'
          '98beb36f9b8cf16e58de2483ea9985e3'
          'd50c1ac47394e9aec637002ef3392bd1'
+         'a091e206b3cadcd9bcd807f3a0c98922'
          '71bbddd5f9799aa045660d92baa05845')
 if [ "$CARCH" != "mips64el" ]; then
     # don't use the Loongson-specific patches on non-mips64el arches.
@@ -64,6 +66,9 @@ prepare() {
   # add realtime patch
   patch -p1 -i "${srcdir}/patch-${_pkgver}-${_rtpatchver}.patch"
 
+  # revert patch, causing the kernel to hang on very early in the boot process
+  patch -p1 -R -i "${srcdir}/timers-do-not-raise-softirq-unconditionally.patch"
+  
   # add freedo as boot logo
   patch -Np1 -i "${srcdir}/boot-logo.patch"
 
diff --git a/kernels/linux-libre-rt/timers-do-not-raise-softirq-unconditionally.patch b/kernels/linux-libre-rt/timers-do-not-raise-softirq-unconditionally.patch
new file mode 100644
index 000000000..d8f01f2d6
--- /dev/null
+++ b/kernels/linux-libre-rt/timers-do-not-raise-softirq-unconditionally.patch
@@ -0,0 +1,156 @@
+From 35b6173e6176fc978c635f9e07f1778eff7b76e7 Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 7 Nov 2013 12:21:11 +0100
+Subject: [PATCH] timers: do not raise softirq unconditionally
+
+Mike,
+
+On Thu, 7 Nov 2013, Mike Galbraith wrote:
+
+> On Thu, 2013-11-07 at 04:26 +0100, Mike Galbraith wrote:
+> > On Wed, 2013-11-06 at 18:49 +0100, Thomas Gleixner wrote:
+>
+> > > I bet you are trying to work around some of the side effects of the
+> > > occasional tick which is still necessary despite of full nohz, right?
+> >
+> > Nope, I wanted to check out cost of nohz_full for rt, and found that it
+> > doesn't work at all instead, looked, and found that the sole running
+> > task has just awakened ksoftirqd when it wants to shut the tick down, so
+> > that shutdown never happens.
+>
+> Like so in virgin 3.10-rt.  Box is x3550 M3 booted nowatchdog
+> rcu_nocbs=1-3 nohz_full=1-3, and CPUs1-3 are completely isolated via
+> cpusets as well.
+
+well, that very same problem is in mainline if you add "threadirqs" to
+the command line. But we can be smart about this. The untested patch
+below should address that issue. If that works on mainline we can
+adapt it for RT (needs a trylock(&base->lock) there).
+
+Though it's not a full solution. It needs some thought versus the
+softirq code of timers. Assume we have only one timer queued 1000
+ticks into the future. So this change will cause the timer softirq not
+to be called until that timer expires and then the timer softirq is
+going to do 1000 loops until it catches up with jiffies. That's
+anything but pretty ...
+
+What worries me more is this one:
+
+  pert-5229  [003] d..h1..   684.482618: softirq_raise: vec=9 [action=RCU]
+
+The CPU has no callbacks as you shoved them over to cpu 0, so why is
+the RCU softirq raised?
+
+Thanks,
+
+	tglx
+------------------
+Message-id: <alpine.DEB.2.02.1311071158350.23353@ionos.tec.linutronix.de>
+|CONFIG_NO_HZ_FULL + CONFIG_PREEMPT_RT_FULL = nogo
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+---
+ include/linux/hrtimer.h |    3 +--
+ kernel/hrtimer.c        |   31 +++++++------------------------
+ kernel/timer.c          |   23 ++++++++++++++++++++---
+ 3 files changed, 28 insertions(+), 29 deletions(-)
+
+--- a/include/linux/hrtimer.h
++++ b/include/linux/hrtimer.h
+@@ -461,9 +461,8 @@ extern int schedule_hrtimeout_range_cloc
+ 		unsigned long delta, const enum hrtimer_mode mode, int clock);
+ extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
+ 
+-/* Soft interrupt function to run the hrtimer queues: */
++/* Called from the periodic timer tick */
+ extern void hrtimer_run_queues(void);
+-extern void hrtimer_run_pending(void);
+ 
+ /* Bootup initialization: */
+ extern void __init hrtimers_init(void);
+--- a/kernel/hrtimer.c
++++ b/kernel/hrtimer.c
+@@ -1694,30 +1694,6 @@ static void run_hrtimer_softirq(struct s
+ }
+ 
+ /*
+- * Called from timer softirq every jiffy, expire hrtimers:
+- *
+- * For HRT its the fall back code to run the softirq in the timer
+- * softirq context in case the hrtimer initialization failed or has
+- * not been done yet.
+- */
+-void hrtimer_run_pending(void)
+-{
+-	if (hrtimer_hres_active())
+-		return;
+-
+-	/*
+-	 * This _is_ ugly: We have to check in the softirq context,
+-	 * whether we can switch to highres and / or nohz mode. The
+-	 * clocksource switch happens in the timer interrupt with
+-	 * xtime_lock held. Notification from there only sets the
+-	 * check bit in the tick_oneshot code, otherwise we might
+-	 * deadlock vs. xtime_lock.
+-	 */
+-	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+-		hrtimer_switch_to_hres();
+-}
+-
+-/*
+  * Called from hardirq context every jiffy
+  */
+ void hrtimer_run_queues(void)
+@@ -1730,6 +1706,13 @@ void hrtimer_run_queues(void)
+ 	if (hrtimer_hres_active())
+ 		return;
+ 
++	/*
++	 * Check whether we can switch to highres mode.
++	 */
++	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())
++	    && hrtimer_switch_to_hres())
++		return;
++
+ 	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+ 		base = &cpu_base->clock_base[index];
+ 		if (!timerqueue_getnext(&base->active))
+--- a/kernel/timer.c
++++ b/kernel/timer.c
+@@ -1439,8 +1439,6 @@ static void run_timer_softirq(struct sof
+ {
+ 	struct tvec_base *base = __this_cpu_read(tvec_bases);
+ 
+-	hrtimer_run_pending();
+-
+ 	if (time_after_eq(jiffies, base->timer_jiffies))
+ 		__run_timers(base);
+ }
+@@ -1450,8 +1448,27 @@ static void run_timer_softirq(struct sof
+  */
+ void run_local_timers(void)
+ {
++	struct tvec_base *base = __this_cpu_read(tvec_bases);
++
+ 	hrtimer_run_queues();
+-	raise_softirq(TIMER_SOFTIRQ);
++	/*
++	 * We can access this lockless as we are in the timer
++	 * interrupt. If there are no timers queued, nothing to do in
++	 * the timer softirq.
++	 */
++	if (!spin_do_trylock(&base->lock)) {
++		raise_softirq(TIMER_SOFTIRQ);
++		return;
++	}
++	if (!base->active_timers)
++		goto out;
++
++	/* Check whether the next pending timer has expired */
++	if (time_before_eq(base->next_timer, jiffies))
++		raise_softirq(TIMER_SOFTIRQ);
++out:
++	rt_spin_unlock_after_trylock_in_irq(&base->lock);
++
+ }
+ 
+ #ifdef __ARCH_WANT_SYS_ALARM